A Task-Space Tracking Control Approach for Duct Cleaning Robot Based on Fuzzy Wavelet Neural Network

Abstract

In this study, a task-space adaptive robust control methodology which takes uncertainties and external disturbances into account is proposed for a class of duct cleaning mobile manipulators. First of all, the configuration of the real duct cleaning robot is introduced, and the Jacobian matrix and the dynamic model of the real robotic system are obtained. Then, the structure of adaptive robust controller based on sliding mode control (SMC) approach and the fuzzy wavelet neural network is detailed, the proposed control approach combines the advantages of SMC which can suppress the external disturbances with the fuzzy wavelet neural network which can compensate the uncertainties by its strong ability to approximate a nonlinear function to an arbitrary accuracy, the stability of the whole robotic control system, the uniformly ultimately boundedness of tracking errors, and the boundedness of fuzzy wavelet neural networks weight estimation errors are all guaranteed based on the Lyapunov stability theory. Finally, simulation results are presented to demonstrate the superior performance of the proposed approach, and experiments are given to illustrate that the proposed approach is useful for real duct cleaning robot system with well performance.